【RVCモデル】v2高品質モデルNo.007「落ち着いた声の女の子」歌唱対応
-
RVC voice i got but didn't work out for me. Maybe it does for someone else
booth: https://booth.pm/en/items/7005474
link: -
It's a japanese model, so probably won't work well unless you speak Japanese with it.
-
Thanks for sharing!!! There's a new RVC version just released like two weeks, maybe you can get better version using new updated RVC
@tapple First official update in almost 3 years! Thanks for letting me know!
Also, the problem with Japanese models, is that the training data usually doesnt contain any audio of the person speaking in English, so every time you use the model and make a sound that wasnt in the training data (typical English sounds, especially with the letter 'r'), it has to retrieve sound from the pretrain instead, which will sound different from the intended voice and thus you end up with a voice that doesnt sound as good as in the sample.
If you could however find a similar enough model that was made with English training data, you could merge that model with this one to 'fill in the blanks' and try out different ratios and end up with something that might sound really good. You could also make an rvc model from your real voice, and then merge it with the Japanese model at a low ratio, where its maybe only 5 or 10% your own voice, and get a big bump in quality.
The last software I tried was Vonovox, which works decently well, and supports SPIN. Im going to download the new RVC and test it out.
-
Thanks for sharing!!! There's a new RVC version just released like two weeks, maybe you can get better version using new updated RVC
@tapple where would you find new rvc? i used this with software called vonovox.
-
@tapple where would you find new rvc? i used this with software called vonovox.
@HertaSimp001 https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/releases/tag/2.3.260718
This is the newest version. I just tested it, and it's supposed to have improved inference quality, but I didn't notice any quality difference from the old one. It is however faster. To start the voice changer, you run go-realtime-gui. -
@HertaSimp001 https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/releases/tag/2.3.260718
This is the newest version. I just tested it, and it's supposed to have improved inference quality, but I didn't notice any quality difference from the old one. It is however faster. To start the voice changer, you run go-realtime-gui.@seraphina1996 you think i should try it or stick with vonovox? Not the best at using github
-
@seraphina1996 you think i should try it or stick with vonovox? Not the best at using github
@HertaSimp001
Vonovox works great, but I think RVC Gui will be faster for you. It also has a resonance shifter, which I dont remember if vonovox has. You dont have to 'use' github. Just open the link and you will see a page with several download links. The top link is if you have an nvidia 20x0-40x0 GPU, and the second link is the download for if you have an nvidia 50x0 gpu. The third download link is for AMD/Intel GPU's.After you download it, unzip it with 7zip to your drive, and run run-web-gui.bat, and it will open a terminal window which says 'if this is the first time running, it maybe take 20 seconds to start', but its written in Chinese, but now you know what it means. Then it should start.
-
@HertaSimp001
Vonovox works great, but I think RVC Gui will be faster for you. It also has a resonance shifter, which I dont remember if vonovox has. You dont have to 'use' github. Just open the link and you will see a page with several download links. The top link is if you have an nvidia 20x0-40x0 GPU, and the second link is the download for if you have an nvidia 50x0 gpu. The third download link is for AMD/Intel GPU's.After you download it, unzip it with 7zip to your drive, and run run-web-gui.bat, and it will open a terminal window which says 'if this is the first time running, it maybe take 20 seconds to start', but its written in Chinese, but now you know what it means. Then it should start.
@seraphina1996 thx will try, i have 50 series and haven't really noticed delay. I had more issue with models that sound normal. If you know any good ones lmk, don't mind if they're paid ones, just afraid to get booth ones after this one didn't fit me.
-
@seraphina1996 thx will try, i have 50 series and haven't really noticed delay. I had more issue with models that sound normal. If you know any good ones lmk, don't mind if they're paid ones, just afraid to get booth ones after this one didn't fit me.
@HertaSimp001 Yeah, unless you speak fluent japanese, that voice model wont work for you.
Regarding quality:
#1: If your rvc is making a lot of garbled noise, you have to put noise cancellation on your mic before it goes into the RVC.
#2: If it's mispronouncing words or slurring, your mic volume is either too high or too low, and it cant hear properly what youre saying.
#3: If you changing your volume doesnt fix it, try playing with the sliders on the right side in rvg-gui. Increasing them tends to increase latency, but might sometimes noticeably improve quality.And yeah, some models are worse than others. I would avoid models trained on voices from tv shows or games, because they usually have a very limited range and break a lot with natural speak. Voice models trained off of youtubers, livestreamers etc. tend to work a lot better.
-
@HertaSimp001 Yeah, unless you speak fluent japanese, that voice model wont work for you.
Regarding quality:
#1: If your rvc is making a lot of garbled noise, you have to put noise cancellation on your mic before it goes into the RVC.
#2: If it's mispronouncing words or slurring, your mic volume is either too high or too low, and it cant hear properly what youre saying.
#3: If you changing your volume doesnt fix it, try playing with the sliders on the right side in rvg-gui. Increasing them tends to increase latency, but might sometimes noticeably improve quality.And yeah, some models are worse than others. I would avoid models trained on voices from tv shows or games, because they usually have a very limited range and break a lot with natural speak. Voice models trained off of youtubers, livestreamers etc. tend to work a lot better.
@seraphina1996 thank your for the detailed explanation, i did notice words mispronounced. I never knew that could have been the problem. I'll mess with the settings. Thanks again!!
Hello! It looks like you're interested in this conversation, but you don't have an account yet.
Getting fed up of having to scroll through the same posts each visit? When you register for an account, you'll always come back to exactly where you were before, and choose to be notified of new replies (either via email, or push notification). You'll also be able to save bookmarks and upvote posts to show your appreciation to other community members.
With your input, this post could be even better 💗
Register Login